chore: initial commit
This commit is contained in:
commit
5e630120f2
|
@ -0,0 +1,3 @@
|
||||||
|
zig-cache/
|
||||||
|
zig-out/
|
||||||
|
.vscode/
|
|
@ -0,0 +1,67 @@
|
||||||
|
const std = @import("std");
|
||||||
|
|
||||||
|
// Although this function looks imperative, note that its job is to
|
||||||
|
// declaratively construct a build graph that will be executed by an external
|
||||||
|
// runner.
|
||||||
|
pub fn build(b: *std.Build) void {
|
||||||
|
// Standard target options allows the person running `zig build` to choose
|
||||||
|
// what target to build for. Here we do not override the defaults, which
|
||||||
|
// means any target is allowed, and the default is native. Other options
|
||||||
|
// for restricting supported target set are available.
|
||||||
|
const target = b.standardTargetOptions(.{});
|
||||||
|
|
||||||
|
// Standard optimization options allow the person running `zig build` to select
|
||||||
|
// between Debug, ReleaseSafe, ReleaseFast, and ReleaseSmall. Here we do not
|
||||||
|
// set a preferred release mode, allowing the user to decide how to optimize.
|
||||||
|
const optimize = b.standardOptimizeOption(.{});
|
||||||
|
|
||||||
|
const exe = b.addExecutable(.{
|
||||||
|
.name = "trie",
|
||||||
|
// In this case the main source file is merely a path, however, in more
|
||||||
|
// complicated build scripts, this could be a generated file.
|
||||||
|
.root_source_file = .{ .path = "src/main.zig" },
|
||||||
|
.target = target,
|
||||||
|
.optimize = optimize,
|
||||||
|
});
|
||||||
|
|
||||||
|
// This declares intent for the executable to be installed into the
|
||||||
|
// standard location when the user invokes the "install" step (the default
|
||||||
|
// step when running `zig build`).
|
||||||
|
exe.install();
|
||||||
|
|
||||||
|
// This *creates* a RunStep in the build graph, to be executed when another
|
||||||
|
// step is evaluated that depends on it. The next line below will establish
|
||||||
|
// such a dependency.
|
||||||
|
const run_cmd = exe.run();
|
||||||
|
|
||||||
|
// By making the run step depend on the install step, it will be run from the
|
||||||
|
// installation directory rather than directly from within the cache directory.
|
||||||
|
// This is not necessary, however, if the application depends on other installed
|
||||||
|
// files, this ensures they will be present and in the expected location.
|
||||||
|
run_cmd.step.dependOn(b.getInstallStep());
|
||||||
|
|
||||||
|
// This allows the user to pass arguments to the application in the build
|
||||||
|
// command itself, like this: `zig build run -- arg1 arg2 etc`
|
||||||
|
if (b.args) |args| {
|
||||||
|
run_cmd.addArgs(args);
|
||||||
|
}
|
||||||
|
|
||||||
|
// This creates a build step. It will be visible in the `zig build --help` menu,
|
||||||
|
// and can be selected like this: `zig build run`
|
||||||
|
// This will evaluate the `run` step rather than the default, which is "install".
|
||||||
|
const run_step = b.step("run", "Run the app");
|
||||||
|
run_step.dependOn(&run_cmd.step);
|
||||||
|
|
||||||
|
// Creates a step for unit testing.
|
||||||
|
const exe_tests = b.addTest(.{
|
||||||
|
.root_source_file = .{ .path = "src/tests.zig" },
|
||||||
|
.target = target,
|
||||||
|
.optimize = optimize,
|
||||||
|
});
|
||||||
|
|
||||||
|
// Similar to creating the run step earlier, this exposes a `test` step to
|
||||||
|
// the `zig build --help` menu, providing a way for the user to request
|
||||||
|
// running the unit tests.
|
||||||
|
const test_step = b.step("test", "Run unit tests");
|
||||||
|
test_step.dependOn(&exe_tests.step);
|
||||||
|
}
|
|
@ -0,0 +1,210 @@
|
||||||
|
//! Hash Array Mapped Trie
|
||||||
|
//! https://idea.popcount.org/2012-07-25-introduction-to-hamt/
|
||||||
|
const std = @import("std");
|
||||||
|
// const Token = @import("Token.zig");
|
||||||
|
|
||||||
|
const Allocator = std.mem.Allocator;
|
||||||
|
const HashArrayMappedTrie = @This();
|
||||||
|
|
||||||
|
const t = 5;
|
||||||
|
const table_size = std.math.powi(u32, 2, t) catch unreachable;
|
||||||
|
|
||||||
|
root: [table_size]?*Node,
|
||||||
|
allocator: Allocator,
|
||||||
|
|
||||||
|
const Node = union(enum) { kv: Pair, table: Table };
|
||||||
|
const Pair = struct { key: []const u8, value: void };
|
||||||
|
const Table = struct { map: u32 = 0, base: [*]Node };
|
||||||
|
|
||||||
|
pub fn init(allocator: Allocator) !HashArrayMappedTrie {
|
||||||
|
return .{
|
||||||
|
.root = [_]?*Node{null} ** table_size,
|
||||||
|
.allocator = allocator,
|
||||||
|
};
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn deinit(self: *HashArrayMappedTrie) void {
|
||||||
|
for (self.root) |node| {
|
||||||
|
if (node == null) continue;
|
||||||
|
|
||||||
|
deinitRecurse(self.allocator, node.?);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
fn deinitRecurse(allocator: Allocator, node: *Node) void {
|
||||||
|
switch (node.*) {
|
||||||
|
.kv => allocator.destroy(node),
|
||||||
|
else => {},
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
fn amtIdx(comptime T: type, bitset: T, offset: u16) std.math.Log2Int(T) {
|
||||||
|
const L2I = std.math.Log2Int(T);
|
||||||
|
|
||||||
|
const shift_amt = @intCast(L2I, @typeInfo(T).Int.bits - offset);
|
||||||
|
return @truncate(L2I, bitset >> shift_amt);
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn search(self: *HashArrayMappedTrie, key: []const u8) ?Pair {
|
||||||
|
const bitset = hash(key);
|
||||||
|
|
||||||
|
// most siginificant t bits from hash
|
||||||
|
var hash_offset: u5 = t;
|
||||||
|
var current: *Node = self.root[amtIdx(u32, bitset, hash_offset)] orelse return null;
|
||||||
|
|
||||||
|
while (true) {
|
||||||
|
switch (current.*) {
|
||||||
|
.table => |table| {
|
||||||
|
hash_offset += t;
|
||||||
|
|
||||||
|
const mask = @as(u32, 1) << amtIdx(u32, bitset, hash_offset);
|
||||||
|
|
||||||
|
if (table.map & mask != 0) {
|
||||||
|
const idx = @popCount(table.map & (mask - 1));
|
||||||
|
|
||||||
|
current = &table.base[idx];
|
||||||
|
} else return null; // hash table entry is empty
|
||||||
|
},
|
||||||
|
.kv => |pair| {
|
||||||
|
if (!std.mem.eql(u8, pair.key, key)) return null;
|
||||||
|
return pair;
|
||||||
|
},
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn insert(self: *HashArrayMappedTrie, comptime key: []const u8, value: void) !void {
|
||||||
|
const bitset = hash(key);
|
||||||
|
|
||||||
|
// most siginificant t bits from hash
|
||||||
|
var hash_offset: u5 = t;
|
||||||
|
const root_idx = amtIdx(u32, bitset, hash_offset);
|
||||||
|
|
||||||
|
var current: *Node = self.root[root_idx] orelse {
|
||||||
|
// node in root table is empty, place the KV here
|
||||||
|
const node = try self.allocator.create(Node);
|
||||||
|
node.* = .{ .kv = .{ .key = key, .value = value } };
|
||||||
|
|
||||||
|
self.root[root_idx] = node;
|
||||||
|
return;
|
||||||
|
};
|
||||||
|
|
||||||
|
while (true) {
|
||||||
|
const mask = @as(u32, 1) << amtIdx(u32, bitset, hash_offset);
|
||||||
|
|
||||||
|
switch (current.*) {
|
||||||
|
.table => |*table| {
|
||||||
|
if (table.map & mask == 0) {
|
||||||
|
// Empty
|
||||||
|
const old_len = @popCount(table.map);
|
||||||
|
const new_base = try self.allocator.alloc(Node, old_len + 1);
|
||||||
|
|
||||||
|
var i: u5 = 0;
|
||||||
|
for (0..@typeInfo(u32).Int.bits) |shift| {
|
||||||
|
const mask_loop = @as(u32, 1) << @intCast(u5, shift);
|
||||||
|
|
||||||
|
if (table.map & mask_loop != 0) {
|
||||||
|
defer i += 1;
|
||||||
|
|
||||||
|
const idx = @popCount(table.map & (mask_loop - 1));
|
||||||
|
const copy = if (mask == mask_loop) Node{ .kv = Pair{ .key = key, .value = value } } else table.base[idx];
|
||||||
|
new_base[i] = copy;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
self.allocator.free(table.base[0..old_len]);
|
||||||
|
table.base = new_base.ptr;
|
||||||
|
table.map |= mask;
|
||||||
|
|
||||||
|
return; // inserted an elemnt into the Trie
|
||||||
|
} else {
|
||||||
|
// Found an entry in the array, continue loop (?)
|
||||||
|
const idx = @popCount(table.map & (mask - 1));
|
||||||
|
current = &table.base[idx];
|
||||||
|
|
||||||
|
hash_offset += t; // Go one layer deper
|
||||||
|
}
|
||||||
|
},
|
||||||
|
.kv => |prev_pair| {
|
||||||
|
const prev_bitset = hash(prev_pair.key);
|
||||||
|
const prev_mask = @as(u32, 1) << amtIdx(u32, prev_bitset, hash_offset);
|
||||||
|
|
||||||
|
const table = switch (std.math.order(mask, prev_mask)) {
|
||||||
|
.lt => blk: {
|
||||||
|
// there are no collisions between the two hash subsets.
|
||||||
|
const pairs = try self.allocator.alloc(Node, 2);
|
||||||
|
pairs[0] = .{ .kv = .{ .key = key, .value = value } };
|
||||||
|
pairs[1] = .{ .kv = prev_pair };
|
||||||
|
|
||||||
|
break :blk .{ .table = .{ .map = mask | prev_mask, .base = pairs.ptr } };
|
||||||
|
},
|
||||||
|
.gt => blk: {
|
||||||
|
// there are no collisions between the two hash subsets.
|
||||||
|
const pairs = try self.allocator.alloc(Node, 2);
|
||||||
|
pairs[0] = .{ .kv = prev_pair };
|
||||||
|
pairs[1] = .{ .kv = .{ .key = key, .value = value } };
|
||||||
|
|
||||||
|
break :blk .{ .table = .{ .map = mask | prev_mask, .base = pairs.ptr } };
|
||||||
|
},
|
||||||
|
.eq => blk: {
|
||||||
|
const copied_pair = try self.allocator.alloc(Node, 1);
|
||||||
|
copied_pair[0] = .{ .kv = prev_pair };
|
||||||
|
|
||||||
|
break :blk .{ .table = .{ .map = mask, .base = copied_pair.ptr } };
|
||||||
|
},
|
||||||
|
};
|
||||||
|
|
||||||
|
current.* = table;
|
||||||
|
},
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
fn walk(node: *const Node, indent: u8) void {
|
||||||
|
switch (node.*) {
|
||||||
|
.kv => |pair| std.debug.print("{}: {any}\n", .{ indent, pair }),
|
||||||
|
.table => |table| {
|
||||||
|
const len = @popCount(table.map);
|
||||||
|
|
||||||
|
for (0..len) |i| {
|
||||||
|
walk(&table.base[i], indent + 1);
|
||||||
|
}
|
||||||
|
},
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
fn hash(key: []const u8) u32 {
|
||||||
|
var result: u32 = 0;
|
||||||
|
for (key) |c| result |= @as(u32, 1) << @intCast(u5, c - 'a');
|
||||||
|
|
||||||
|
return result;
|
||||||
|
}
|
||||||
|
|
||||||
|
test "insert doesn't panic" {
|
||||||
|
var trie = try HashArrayMappedTrie.init(std.testing.allocator);
|
||||||
|
defer trie.deinit();
|
||||||
|
|
||||||
|
try trie.insert("hello", {});
|
||||||
|
}
|
||||||
|
|
||||||
|
test "search doesn't panic" {
|
||||||
|
var trie = try HashArrayMappedTrie.init(std.testing.allocator);
|
||||||
|
defer trie.deinit();
|
||||||
|
|
||||||
|
std.debug.assert(trie.search("hello") == null);
|
||||||
|
}
|
||||||
|
|
||||||
|
test "insert then search" {
|
||||||
|
var trie = try HashArrayMappedTrie.init(std.heap.page_allocator);
|
||||||
|
defer trie.deinit();
|
||||||
|
|
||||||
|
// Basic Usage
|
||||||
|
try trie.insert("hello", {});
|
||||||
|
const test1 = trie.search("hello").?;
|
||||||
|
try std.testing.expectEqual(Pair{ .key = "hello", .value = {} }, test1);
|
||||||
|
|
||||||
|
// Collision in Root Node
|
||||||
|
try trie.insert("helloworld", {});
|
||||||
|
const test2 = trie.search("helloworld").?;
|
||||||
|
try std.testing.expectEqual(Pair{ .key = "helloworld", .value = {} }, test2);
|
||||||
|
}
|
|
@ -0,0 +1,10 @@
|
||||||
|
const std = @import("std");
|
||||||
|
const HashArrayMappedTrie = @import("HashArrayMappedTrie.zig");
|
||||||
|
|
||||||
|
pub fn main() !void {
|
||||||
|
var trie = try HashArrayMappedTrie.init(std.heap.page_allocator);
|
||||||
|
defer trie.deinit();
|
||||||
|
|
||||||
|
try trie.insert("hello", {});
|
||||||
|
try trie.insert("helloworld", {});
|
||||||
|
}
|
|
@ -0,0 +1,8 @@
|
||||||
|
comptime {
|
||||||
|
_ = @import("HashArrayMappedTrie.zig");
|
||||||
|
_ = @import("main.zig");
|
||||||
|
}
|
||||||
|
|
||||||
|
test {
|
||||||
|
@import("std").testing.refAllDecls(@This());
|
||||||
|
}
|
Loading…
Reference in New Issue